Fire in da houseTop Tip:Most people pay up to $340 per month for Perplexity, MidJourney, Runway, ChatGPT, and more - but you can get them all your AI tools for $15 with Galaxy. It's free to test!Fire in da houseCheck it out

MCPControl

MCP.Pizza Chef: Cheffromspace

MCPControl is a specialized MCP server designed exclusively for Windows OS automation. It provides programmatic control over essential system operations such as mouse movements, keyboard inputs, window management, and screen capture. By bridging AI models with Windows system controls, MCPControl enables seamless automation workflows and real-time interaction with the operating system. Although currently de-prioritized and maintained as an experimental project, it remains a valuable tool for developers seeking to integrate AI-driven automation into Windows environments. MCPControl supports the Model Context Protocol, facilitating secure and structured communication between AI agents and Windows system functions.

Use This MCP server To

Automate mouse and keyboard inputs on Windows Manage and manipulate application windows programmatically Capture screenshots for visual context or analysis Enable AI agents to interact with Windows OS environment Integrate Windows system control into AI workflows

README

MCPControl

Project Status: De-prioritized. This project was created as an experiment, but Windows automation isn't something I'm looking to get deep into. I will review and merge PRs but will not be adding features soon. May revisit in the future. Looking for a maintainer.

MCPControl Logo

Latest Release

Windows control server for the Model Context Protocol, providing programmatic control over system operations including mouse, keyboard, window management, and screen capture functionality.

Note: This project currently supports Windows only.

πŸ”₯ Why MCPControl?

MCPControl bridges the gap between AI models and your desktop, enabling secure, programmatic control of:

  • πŸ–±οΈ Mouse movements and clicks
  • ⌨️ Keyboard input and shortcuts
  • πŸͺŸ Window management
  • πŸ“Έ Screen capture and analysis
  • πŸ“‹ Clipboard operations

πŸ”Œ Quick Start

  1. Install Node.js (if not already installed)

    # Visit https://nodejs.org and download the latest LTS version
    
  2. Configure MCP settings in your Claude client:

    {
      "mcpServers": {
        "MCPControl": {
          "command": "npx",
          "args": [
            "--no-cache",
            "-y",
            "mcp-control"
          ]
        }
      }
    }
  3. Restart your client and MCPControl will appear in your MCP menu!

πŸš€ Popular Use Cases

Assisted Automation

  • Application Testing: Delegate repetitive UI testing to Claude, allowing AI to navigate through applications and report issues
  • Workflow Automation: Have Claude operate applications on your behalf, handling repetitive tasks while you focus on creative work
  • Form Filling: Let Claude handle data entry tasks with your supervision

AI Experimentation

  • AI Gaming: Watch Claude learn to play simple games through visual feedback
  • Visual Reasoning: Test Claude's ability to navigate visual interfaces and solve visual puzzles
  • Human-AI Collaboration: Explore new interaction paradigms where Claude can see your screen and help with complex tasks

Development and Testing

  • Cross-Application Integration: Bridge applications that don't normally communicate
  • UI Testing Framework: Create robust testing scenarios with visual validation
  • Demo Creation: Automate the creation of product demonstrations

⚠️ IMPORTANT DISCLAIMER

THIS SOFTWARE IS EXPERIMENTAL AND POTENTIALLY DANGEROUS

By using this software, you acknowledge and accept that:

  • Giving AI models direct control over your computer through this tool is inherently risky
  • This software can control your mouse, keyboard, and other system functions which could potentially cause unintended consequences
  • You are using this software entirely at your own risk
  • The creators and contributors of this project accept NO responsibility for any damage, data loss, or other consequences that may arise from using this software
  • This tool should only be used in controlled environments with appropriate safety measures in place

USE AT YOUR OWN RISK

🌟 Features

πŸͺŸ Window Management

  • List all windows
  • Get active window info
  • Focus, resize & reposition

πŸ–±οΈ Mouse Control

  • Precision movement
  • Click & drag operations
  • Scrolling & position tracking

⌨️ Keyboard Control

  • Text input & key combos
  • Key press/release control
  • Hold key functionality

πŸ“Έ Screen Operations

  • High-quality screenshots
  • Screen size detection
  • Active window capture

πŸ› οΈ Development Setup

If you're interested in contributing or building from source, please see CONTRIBUTING.md for detailed instructions.

Development Requirements

To build this project for development, you'll need:

  1. Windows operating system (required for the keysender dependency)
  2. Node.js 18 or later (install using the official Windows installer which includes build tools)
  3. npm package manager
  4. Native build tools:
    • node-gyp: npm install -g node-gyp
    • cmake-js: npm install -g cmake-js

The keysender dependency relies on Windows-specific native modules that require these build tools.

πŸ“‹ Project Structure

  • /src
    • /handlers - Request handlers and tool management
    • /tools - Core functionality implementations
    • /types - TypeScript type definitions
    • index.ts - Main application entry point

πŸ”– Repository Branches

  • main - Main development branch with the latest features and changes
  • release - Stable release branch that mirrors the latest stable tag (currently v0.1.22)

Version Installation

You can install specific versions of MCPControl using npm:

# Install the latest stable release (from release branch)
npm install mcp-control

# Install a specific version
npm install mcp-control@0.1.22

πŸ“š Dependencies

  • @modelcontextprotocol/sdk - MCP SDK for protocol implementation
  • keysender - Windows-only UI automation library
  • clipboardy - Clipboard handling
  • sharp - Image processing
  • uuid - UUID generation

🚧 Known Limitations

  • Window minimize/restore operations are currently unsupported
  • Multiple screen functions may not work as expected, depending on setup
  • The get_screenshot utility does not work with the VS Code Extension Cline. See GitHub issue #1865
  • Some operations may require elevated permissions depending on the target application
  • Only Windows is supported
  • MCPControl works best at 1280x720 resolution, single screen. Click accuracy is optimized for this resolution. We're working on an offset/scaling bug and looking for testers or help creating testing tools

πŸ‘₯ Contributing

See CONTRIBUTING.md

Note: As this project is currently in a maintenance-only mode, we're primarily focusing on bug fixes. However, fully implemented and well-tested features will be considered for merging. Looking for maintainers to help keep the project active.

βš–οΈ License

This project is licensed under the MIT License - see the LICENSE file for details.

πŸ“– References

  • Model Context Protocol Documentation

MseeP.ai Security Assessment Badge

MCPControl FAQ

Is MCPControl compatible with operating systems other than Windows?
No, MCPControl currently supports Windows OS exclusively.
Can MCPControl capture screenshots for AI analysis?
Yes, it provides screen capture functionality to support visual context.
Is MCPControl actively maintained and receiving new features?
The project is currently de-prioritized; PRs are reviewed but new features are not actively developed.
How does MCPControl interact with AI models?
It exposes Windows system controls via the Model Context Protocol, enabling AI models to automate OS tasks.
Can MCPControl manage multiple windows simultaneously?
Yes, it supports programmatic window management including moving, resizing, and focusing windows.
Does MCPControl support secure and scoped interactions?
Yes, as an MCP server, it follows MCP principles for secure and observable model interactions.
Where can I find the latest release of MCPControl?
The latest release is available on its GitHub repository under the releases section.
Can MCPControl be integrated with different LLM providers?
Yes, it works with any MCP-compatible AI models, including OpenAI, Claude, and Gemini.